>>
Run Hy4-preview on Lium
Tencent · Text generation · 780B parameters · 1560 GB BF16 weights · released 2026-08-27
It needs about 1872 GB of VRAM. The cheapest setup that runs it is 8x B300 SXM6 (2304 GB), reference $64.00 per hour, billed per second.
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve tencent/Hy4-preview:
vllm serve tencent/Hy4-preview --tensor-parallel-size 8Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does Hy4-preview need?
About 1560 GB for the released BF16 weights, so plan on 1872 GB with room for activations and KV cache at a short context. Longer contexts and bigger batches need more.
What GPU should I rent to run Hy4-preview?
8x B300 SXM6 (2304 GB). On Lium that setup costs reference $64.00 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt